2.69秒完成全身骨骼分割，速度比传统方法快25倍。
Bonnet: Ultra-fast whole-body bone segmentation from CT scans
- 基于HU阈值与稀疏卷积U-Net，分块推理实现快速分割
- 在肋骨、骨盆、脊柱上达到高重合率，平均耗时仅2.69秒
- 适合手术规划等对速度敏感的临床场景
本文提出Bonnet，一种超快速的稀疏体积管道，用于从CT扫描中进行全身骨骼分割。准确的骨骼分割对于手术规划和解剖分析至关重要，但现有的3D体素模型如nnU-Net和STU-Net计算量大，单次扫描通常需数分钟，限制了其在时间敏感场景中的应用。Bonnet通过集成一系列新组件——基于HU的骨骼阈值化、基于稀疏spconv的U-Net分块推理，以及多窗口融合——实现了全体积预测。在TotalSegmentator上训练，并在RibSeg、CT-Pelvic1K和CT-Spine1K上无需额外调优评估，Bonnet在肋骨、骨盆和脊柱上均取得高Dice分数，且在RTX A6000上每扫描仅需2.69秒。相比强基准的体素模型，其精度相当，但在相同硬件和分块设置下推理时间减少约25倍。工具包与预训练模型将开源发布于https://github.com/HINTLab/Bonnet。
原文摘要 · Abstract (English)
This work proposes Bonnet, an ultra-fast sparse-volume pipeline for whole-body bone segmentation from CT scans. Accurate bone segmentation is important for surgical planning and anatomical analysis, but existing 3D voxel-based models such as nnU-Net and STU-Net require heavy computation and often take several minutes per scan, which limits time-critical use. The proposed Bonnet addresses this by integrating a series of novel framework components including HU-based bone thresholding, patch-wise inference with a sparse spconv-based U-Net, and multi-window fusion into a full-volume prediction. Trained on TotalSegmentator and evaluated without additional tuning on RibSeg, CT-Pelvic1K, and CT-Spine1K, Bonnet achieves high Dice across ribs, pelvis, and spine while running in only 2.69 seconds per scan on an RTX A6000. Compared to strong voxel baselines, Bonnet attains a similar accuracy but reduces inference time by roughly 25x on the same hardware and tiling setup. The toolkit and pre-trained models will be released at https://github.com/HINTLab/Bonnet.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。